English

Street Scene: A new dataset and evaluation protocol for video anomaly detection

Computer Vision and Pattern Recognition 2020-01-27 v3

Abstract

Progress in video anomaly detection research is currently slowed by small datasets that lack a wide variety of activities as well as flawed evaluation criteria. This paper aims to help move this research effort forward by introducing a large and varied new dataset called Street Scene, as well as two new evaluation criteria that provide a better estimate of how an algorithm will perform in practice. In addition to the new dataset and evaluation criteria, we present two variations of a novel baseline video anomaly detection algorithm and show they are much more accurate on Street Scene than two state-of-the-art algorithms from the literature.

Keywords

Cite

@article{arxiv.1902.05872,
  title  = {Street Scene: A new dataset and evaluation protocol for video anomaly detection},
  author = {Bharathkumar Ramachandra and Michael Jones},
  journal= {arXiv preprint arXiv:1902.05872},
  year   = {2020}
}

Comments

accepted to WACV 2020